can1357 b93d1929db fix(edit-benchmark): corrected benchmark statistics by filtering ghost runs with zero activity ...

- Excluded ghost runs (failed runs with zero activity) from benchmark statistics to prevent skewed averages.
- Introduced isGhostRun() helper function to identify and filter runs with no tokens or tool calls.
- Updated report generation and task summarization to use nonGhostRuns for all metric calculations.

2026-04-06 18:48:15 +02:00

..

src

fix(edit-benchmark): corrected benchmark statistics by filtering ghost runs with zero activity

2026-04-06 18:48:15 +02:00

test

refactor(edit-benchmark): migrated to typescript with in-process client support

2026-04-06 18:39:04 +02:00

fixtures.tar.gz

refactor(edit-benchmark): migrated to typescript with in-process client support

2026-04-06 18:39:04 +02:00

package.json

refactor(edit-benchmark): migrated to typescript with in-process client support

2026-04-06 18:39:04 +02:00

tsconfig.json

refactor(edit-benchmark): migrated to typescript with in-process client support

2026-04-06 18:39:04 +02:00

tsconfig.publish.json

refactor(edit-benchmark): migrated to typescript with in-process client support

2026-04-06 18:39:04 +02:00